VEMOCLAP: A video emotion classification web application

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sulun, Serkan, Viana, Paula, Davies, Matthew E. P.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914994246909952
author Sulun, Serkan
Viana, Paula
Davies, Matthew E. P.
author_facet Sulun, Serkan
Viana, Paula
Davies, Matthew E. P.
contents We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21303
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VEMOCLAP: A video emotion classification web application
Sulun, Serkan
Viana, Paula
Davies, Matthew E. P.
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
Image and Video Processing
We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app.
title VEMOCLAP: A video emotion classification web application
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
Image and Video Processing
url https://arxiv.org/abs/2410.21303